«
»

Confidence score with Hebrew

A few hours ago, I created a sample Hebrew PLS dictionary. It is very short, but it shows the concept.

hebrew

1. I imported the Hebrew PLS dictionary into simon.
2. I dragged each word to the right side for training.
3. The recorded Hebrew words are stored in the folder /home/liberty/.kde/share/apps/simon/model/training.data.
4. After starting ksimond (PDF), I pressed the Synchronize button.
5. Then I activated simon.
6. When dictating several words, simon is not sure which word is the right one. Is it מדפסת, or is it עִבְרִית? Unfortunately, I didn’t get any output in gedit or in Geany. Maybe it has something to do with the right-to-left encoding?

You can see that thanks to UTF-8 Hebrew shouldn’t be a big problem. I don’t know what went wrong with the missing output. But at least the Hebrew words are displayed correctly, so only the last step is missing.

If anyone is interested in building an Hebrew PLS dictionary, I propose you take a look into the Hebrew Voxforge prompts. I suggest that you take the words that are contained in the prompts into the dictionary. You can take my sample Hebrew dictionary, and expand it. Later, you can use the Voxforge prompts for training (after you have made your first experiences with simon).

Tags: , , , ,

This entry was posted on Thursday, September 10th, 2009 at 8:09 am and is filed under Ubuntu, dictionary. You can follow any responses to this entry through the RSS 2.0 feed. Both comments and pings are currently closed.

2 Responses to “Confidence score with Hebrew”

  1. Peter Grasch says:
    September 10, 2009 at 9:15 pm

    Haha love the did-you-mean dialog!

    I am, however, not surprised about the missing output. simon has only one way to simulate output and this is by simulating _keystrokes_. It can only send keys that it knows how to generate on a conventional keyboard. I taught him some tricks like á, à (dead keys) but apart from that, simon just doesn’t know what the keys are composed of. In case of hebrew the thing gets _very_ tricky. As the keys should be generated with some alt-codes (I assume) that would take a HUGE matrix with all the codes in it. And I guess that matrix will be different on different keyboard setups…

    Maybe you could check if there is some sort of standard where all the alt-codes are defined and if they are the same accross different keyboard layouts and operating systems?

    Greetings,
    Peter

  2. producer says:
    September 14, 2009 at 9:37 am

    Maybe it would help to install Hebrew via System > Administration > Language Support.